Home | Trees | Indices | Help |
|
---|
|
object --+ | CMAAdaptSigmaBase --+ | CMAAdaptSigmaTPA
two point adaptation for step-size sigma. Relies on a specific sampling of the first two offspring, whose objective function value ranks are used to decide on the step-size change.
>>> import cma >>> cma.CMAOptions('adapt').pprint() >>> es = cma.CMAEvolutionStrategy(10 * [0.2], 0.1, {'AdaptSigma': cma.CMAAdaptSigmaTPA, 'ftarget': 1e-8}) >>> es.optimize(cma.fcts.rosen) >>> assert 'ftarget' in es.stop() >>> assert es.result()[1] <= 1e-8 >>> assert es.result()[2] < 6500 # typically < 5500
References: loosely based on Hansen 2008, CMA-ES with Two-Point Step-Size Adaptation, more tightly based on an upcoming paper by Hansen et al.
|
|||
|
|||
|
|||
|
|||
Inherited from Inherited from Inherited from |
|
|||
Inherited from |
|
x.__init__(...) initializes x; see help(type(x)) for signature
|
|
Home | Trees | Indices | Help |
|
---|
Generated by Epydoc 3.0.1 on Tue Mar 3 01:17:17 2015 | http://epydoc.sourceforge.net |